Printer automatic calibration method, device, equipment and medium
By acquiring the characteristics of the printed test images and scanned images, and using deep learning technology to automatically calibrate printer parameters, the problems of poor calibration adaptability and high cost in the prior art are solved, and efficient and automatic printer calibration is achieved.
Patent Information
- Application Number
- CN202411916367.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-24
- Publication Date
- 2025-04-18
AI Technical Summary
Existing printer calibration solutions are poorly adaptable and costly, making it difficult to effectively adapt to the specific differences between different batches of equipment, and require a lot of manpower and time.
By obtaining the inspection features of the printed test images and the inspection features of the scanned images, the printer's printing parameters are automatically calibrated using technologies such as full convolutional neural network and long and short-term memory network.
The printing parameters of different batches of printers are adjusted to varying degrees, which improves the adaptability of calibration, and reduces labor consumption and time through automated processes and reduces calibration costs.
Smart Images
Figure CN119854419A_ABST
Abstract
Description
Technical Field
[0001] The present application belongs to the technical field of printers, and in particular, relates to a method, device, equipment and medium for automatic calibration of a printer. Background Art
[0002] Laser printers or inkjet printers, especially color printers, are affected by many factors during the printing process, resulting in differences in printing results between different batches of printers. These influencing factors mainly include the following aspects:
[0003] 1. Equipment differences: Each laser printer device has slight differences in the manufacturing process;
[0004] 2. Toner charging parameters: Different batches of toner have different charging properties;
[0005] 3. Toner cartridge performance: The degree of wear and performance of the toner cartridge has a significant impact on the printing effect;
[0006] 4. Seasonal factors: Environmental conditions such as temperature and humidity will also affect the printing effect.
[0007] At present, manufacturers generally use universal calibration solutions to calibrate printers, which have the following problems:
[0008] 1. Poor adaptability: The universal calibration solution is difficult to adapt to the specific differences of different batches of equipment and has poor robustness;
[0009] 2. High cost: Manually adjusting the printer calibration for each batch requires a lot of time and manpower costs, which puts a burden on business operations. Summary of the invention
[0010] The embodiments of the present application provide a method, device, equipment and medium for automatic calibration of a printer, which can solve the problems of poor adaptability of printer calibration solutions and high calibration costs.
[0011] In a first aspect, an embodiment of the present application provides a method for automatic calibration of a printer, comprising:
[0012] obtaining inspection features of a printed test image;
[0013] Scanning the printed content on the print medium output by the printer to obtain a scanned image; the printed content is obtained by the printer printing a print test image on the print medium;
[0014] obtaining inspection features of the scanned image;
[0015] The printing parameters of the printer are automatically calibrated based on the verification features of the scanned image and the verification features of the printed test image.
[0016] Optionally, obtain inspection features of the scanned image, including:
[0017] Acquire a frequency domain image of the scanned image;
[0018] taking at least one of the scanned image and the frequency domain image as a test object;
[0019] Acquire feature information of the inspection object and use the feature information of the inspection object as the inspection feature of the scanned image.
[0020] Optionally, a frequency domain image of the scanned image is obtained, including:
[0021] Perform Fourier transform on the scanned image to obtain a frequency domain image of the scanned image.
[0022] Optionally, if the inspection object is a scanned image; obtaining feature information of the inspection object includes:
[0023] A fully convolutional neural network is used to extract features from the scanned image, and a gated recurrent unit is used to calculate the extracted features to obtain the feature information of the scanned image.
[0024] Optionally, if the inspection object is a frequency domain image; obtaining characteristic information of the inspection object includes:
[0025] Performing filtering processing on the frequency domain image, and dividing the filtered frequency domain image into L frequency domain images;
[0026] Use the long short-term memory network to calculate each frequency domain image and obtain the hidden state vector corresponding to each frequency domain image;
[0027] Perform weighted averaging on the hidden state vectors corresponding to the L frequency domain images;
[0028] The long short-term memory network is used to calculate the results of weighted average processing to obtain the characteristic information of the frequency domain image.
[0029] Optionally, automatically calibrating the printing parameters of the printer based on the inspection features of the scanned image and the inspection features of the printed test image, including:
[0030] calculating a print loss of the printed test image based on the inspection features of the scanned image and the inspection features of the printed test image;
[0031] The printing parameters of the printer are updated using the gradient descent method, and the printer is controlled to print a print test image on a print medium using the updated print parameters, and the step of returning to scan the print content on the print medium output by the printer to obtain a scanned image is performed until the printing loss of the print test image converges, and the printing parameters when the printing loss converges are used as the printing parameters after the printer is calibrated.
[0032] Optionally, calculating the printing loss of the printed test image based on the inspection features of the scanned image and the inspection features of the printed test image includes:
[0033] The inspection features of the scanned image and the inspection features of the printed test image are calculated by the cross entropy loss function to obtain the printing loss of the printed test image.
[0034] In a second aspect, an embodiment of the present application provides a device for automatic calibration of a printer, comprising:
[0035] A first acquisition module, used for acquiring inspection features of a printed test image;
[0036] The scanning module is used to scan the printed content on the printing medium output by the printer to obtain a scanned image; the printed content is obtained by the printer printing a print test image on the printing medium;
[0037] A second acquisition module is used to acquire the inspection features of the scanned image;
[0038] The calibration module is used to automatically calibrate the printing parameters of the printer based on the inspection features of the scanned image and the inspection features of the printed test image.
[0039] In a third aspect, an embodiment of the present application provides a terminal device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned printer automatic calibration method when executing the computer program.
[0040] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the above-mentioned printer automatic calibration method is implemented.
[0041] The above solution of the present application has the following beneficial effects:
[0042] In an embodiment of the present application, the print content output by the printer is scanned to obtain a scanned image, and based on the inspection features of the scanned image and the original print test image corresponding to the scanned image, the print parameters of the printer are automatically calibrated. Among them, since the print parameters are calibrated in combination with the print content output by the current printer and the original print test image, the print parameters of different batches of printers can be adjusted to different degrees, making the automatic printer calibration method of the present application highly adaptable. At the same time, since the calibration process is automatic, it can greatly reduce manpower consumption, shorten calibration time, and achieve the effect of reducing calibration costs.
[0043] Other beneficial effects of the present application will be described in detail in the subsequent specific implementation section. BRIEF DESCRIPTION OF THE DRAWINGS
[0044] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.
[0045] Figure 1 A flowchart of a method for automatic calibration of a printer provided in an embodiment of the present application;
[0046] Figure 2 A schematic diagram of the structure of a printer automatic calibration device provided in one embodiment of the present application;
[0047] Figure 3 A schematic diagram of the structure of a terminal device provided in one embodiment of the present application. DETAILED DESCRIPTION
[0048] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.
[0049] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.
[0050] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.
[0051] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.
[0052] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.
[0053] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.
[0054] In view of the problems of poor adaptability and high calibration cost of the printer calibration scheme in the existing printing parameter calibration process, the embodiment of the present application provides a printer automatic calibration method, which scans the print content output by the printer to obtain a scanned image, and automatically calibrates the printing parameters of the printer based on the inspection features of the scanned image and the original print test image corresponding to the scanned image. Among them, since the calibration of the printing parameters is carried out in combination with the print content output by the current printer and the original print test image, the printing parameters of different batches of printers can be adjusted to different degrees, making the printer automatic calibration method of the present application highly adaptable. At the same time, since the calibration process is carried out automatically, it can greatly reduce manpower consumption, shorten the calibration time, and achieve the effect of reducing the calibration cost.
[0055] The specific form of the printer is not limited in the present application, and it can be any form of printer such as a laser printer, an inkjet printer, etc.
[0056] The printer automatic calibration method provided by the present application is exemplarily described below in conjunction with specific embodiments.
[0057] like Figure 1 As shown, the printer automatic calibration method provided in the embodiment of the present application includes the following steps:
[0058] Step 11, obtaining the inspection features of the printed test image.
[0059] The printed test image may be a commonly used test image for a printer (the test image may be an RGB image), which is mainly used to verify the performance and color reproduction capability of the printer. By printing the test image, the user can check whether the printer functions normally, ensure that the color quality meets the requirements, and identify possible printing problems, such as uneven colors, stripes, etc.
[0060] The above-mentioned inspection features are specific contents in the printed test image that are unique and easy to track and compare, and mainly include the color features, texture features, shape features, and spatial relationship features of the printed test image, etc. The process of obtaining the inspection features will be described in detail later.
[0061] Step 12: Scan the printed content on the print medium output by the printer to obtain a scanned image.
[0062] The above-mentioned printed content is obtained by the printer printing a print test image on a print medium. The print medium may be ordinary paper, photo paper, etc. In some embodiments, a scanning module (such as a scanning camera) may be used to scan the printed content to obtain a scanned image.
[0063] In some embodiments of the present application, a paper feeding module (such as a conveying mechanism) can be set at the output port of the printer, and the paper feeding module can transfer the print medium output by the printer to the scanning module, so that the scanning module can scan the printed print medium to obtain a scanned image. The scanned image can specifically be an RGB image or a grayscale image.
[0064] Step 13, obtaining inspection features of the scanned image.
[0065] The inspection features of the scanned image are specific contents in the scanned image that are unique and easy to track and compare, and mainly include color features, texture features, shape features, and spatial relationship features of the scanned image. The process of obtaining the inspection features will be described in detail later.
[0066] Step 14: Automatically calibrate the printing parameters of the printer based on the inspection features of the scanned image and the inspection features of the printed test image.
[0067] In some embodiments of the present application, the scanned image and the test image can be compared based on the inspection features of the scanned image and the printed test image, and the printing parameters can be dynamically adjusted according to the comparison results to complete the automatic calibration of the printing parameters. The above-mentioned printing parameters include nozzle ink droplets, fixing temperature, power-on voltage, etc.
[0068] It is worth mentioning that, since the printing parameters are calibrated in combination with the print content output by the current printer and the original print test image, the printing parameters of different batches of printers can be adjusted to different degrees during the calibration process, making the automatic printer calibration method of the present application highly adaptable. At the same time, since the calibration process is automatic, compared with the existing general calibration scheme, it can greatly reduce manpower consumption, shorten the calibration time, and achieve the effect of reducing calibration costs.
[0069] The following is an exemplary description of the process of obtaining the inspection features.
[0070] Specifically, the specific implementation method of the above step 13, obtaining the inspection features of the scanned image, includes the following steps:
[0071] Step 13.1, obtaining a frequency domain image of the scanned image.
[0072] In some embodiments, a frequency domain image of the scanned image can be obtained by performing Fourier transform on the scanned image to convert a one-dimensional signal into a two-dimensional signal, so as to better detect changes in the scanned image under continuous conditions and evaluate the color difference generated in the continuous images.
[0073] Step 13.2: taking at least one of the scanned image and the frequency domain image as a test object.
[0074] Step 13.3, obtaining feature information of the inspection object, and using the feature information of the inspection object as the inspection feature of the scanned image.
[0075] It can be understood that if the inspection object is a scanned image, the inspection features of the scanned image are the feature information of the scanned image; if the inspection object is a frequency domain image, the inspection features of the scanned image are the feature information of the frequency domain image; if the inspection object includes a scanned image and a frequency domain image, the inspection features of the scanned image include the feature information of the scanned image and the feature information of the frequency domain image.
[0076] In some embodiments of the present application, the specific implementation method of obtaining the feature information of the scanned image is: using a fully convolutional neural network (FCN) to extract features from the scanned image, and using a gated recurrent unit (GRU) to calculate the extracted features to obtain the feature information of the scanned image.
[0077] In practical applications, the scanned image S (1) Divide it into L segments, then use the fully convolutional neural network to extract features from each segment, and use the gated recurrent unit to calculate the extracted L features to obtain the feature information of the scanned image. The specific calculation formula is as follows:
[0078]
[0079] In the above formula, The scanned image S (1) The first fragment of To use the fully convolutional neural network to The features obtained by feature extraction are The scanned image S (1) The Lth fragment of To use the fully convolutional neural network to The features obtained by feature extraction are To use GRU The feature information obtained by calculation is the first part of the feature information of the scanned image. To use GRU The feature information obtained by calculation is the Lth part of the feature information of the scanned image.
[0080] Among them, the parameters of the fully convolutional neural network can be adjusted according to different images. Here is an experimental parameter: 9 convolutional layers, filters for each layer: 16, 16, 32, 32, 64, 64, 128, 128, 256, 256. The purpose of this is to avoid losing the number of features during the convolution process. The reason for using FCN here is that the fully convolutional neural network is mainly used for image segmentation tasks. Compared with the traditional convolutional neural network, FCN does not have a fully connected layer, but replaces all layers with convolutional layers, which can retain the spatial structure information of the input image, so that the network can simultaneously predict the category label of each pixel. The reason for the continuous increase in filters is that as the number of network layers increases, the output dimension of each layer will gradually decrease. In order to compensate for the gradually decreasing induced feature map, multiple convolution kernels can be used in the first few layers or the number of convolution kernels can be gradually increased to better capture the relationship between features. The reason for using GRU is that it is a commonly used recurrent neural network structure with good convergence and stability, and the recurrent network can be calibrated in both forward and reverse directions to obtain a more robust output.
[0081] In some embodiments of the present application, the specific implementation method of obtaining the characteristic information of the frequency domain image is: first, the frequency domain image is filtered, and the filtered frequency domain image is divided into L frequency domain images; then, each frequency domain image is calculated using a long short-term memory network to obtain a hidden state vector corresponding to each frequency domain image; then, the hidden state vectors corresponding to the L frequency domain images are weighted averaged; finally, the result of the weighted average processing is calculated using a long short-term memory network to obtain the characteristic information of the frequency domain image.
[0082] Among them, for the frequency domain image S (2)The purpose of filtering is to eliminate noise and obtain the filtered frequency domain image S′. The calculation formula for the hidden state vector corresponding to each frequency domain image is obtained by using the long short-term memory network: (Z 1 ,...,Z L ) = LSTM(S′) 1 ,...,S′ L ); The calculation formula for weighted averaging of the hidden state vectors corresponding to L frequency domain images is: Finally, the weighted average processing result x is processed by long short-term memory network (2) By calculating, we can get the characteristic information of the frequency domain image x (2) is a matrix. Among them, S′ 1 is the first segment of S′, S′ L is the Lth segment of S′, and LSTM is the long short-term memory network for segment S′ 1 To S′ L Calculate, Z 1 To use the long short-term memory network to segment S′ 1 The hidden state vector Z is extracted by calculation. L To use the long short-term memory network to segment S′ L The hidden state vector extracted by calculation, α t is the weight, α t Can be specified by the point (ie Z t ) and a random point (which can be a vectorized representation of the test image) and can also be set according to actual conditions. The result x of weighted average processing using long short-term memory network (2) The feature information calculated by the first element in is the first part of the feature information of the frequency domain image. To use the long short-term memory network to (2) The feature information obtained by calculating the Lth element in is the Lth part of the feature information of the frequency domain image.
[0083] It should be noted that the inspection features of the printed test image are the same as the inspection features of the scanned image. The inspection features of the printed test image can be feature information of the printed test image, feature information of the frequency domain image of the printed test image, or feature information of the frequency domain image of the printed test image. The feature information of the printed test image is obtained in the same manner as the feature information of the scanned image, and the feature information of the frequency domain image of the printed test image is obtained in the same manner as the feature information of the frequency domain image of the scanned image. To avoid excessive repetition, the process of obtaining the feature information of the printed test image and the feature information of the frequency domain image of the printed test image will not be described in detail.
[0084] The following is an exemplary description of the process of automatically calibrating the printing parameters of the printer based on the inspection features of the scanned image and the inspection features of the printed test image.
[0085] Specifically, the specific implementation process of the above step 14, automatically calibrating the printing parameters of the printer based on the inspection features of the scanned image and the inspection features of the printed test image, includes the following steps:
[0086] Step 14.1, calculating the printing loss of the printed test image based on the inspection features of the scanned image and the inspection features of the printed test image.
[0087] Specifically, the inspection features of the scanned image and the inspection features of the printed test image can be calculated by the cross entropy loss function to obtain the printing loss of the printed test image. Specifically, the formula The printing loss of the printed test image is calculated, where y l is the lth part of the inspection feature of the scanned image, The first part of the inspection feature of the printed test image.
[0088] It should be noted that, when calculating the printing loss, if the inspection feature of the scanned image uses the feature information of the scanned image, then the inspection feature of the printed test image is also the feature information of the printed test image; if the inspection feature of the scanned image uses the feature information of the frequency domain image, then the inspection feature of the printed test image is also the feature information of the frequency domain image; if the inspection feature of the scanned image includes the feature information of the scanned image and the corresponding frequency domain image, then the inspection feature of the printed test image also includes the feature information of the printed test image and the corresponding frequency domain image. In this case, y l It can be the weighted average of the lth part of the characteristic information of the scanned image and the lth part of the characteristic information of the corresponding frequency domain image, It is the weighted average of the lth part of the characteristic information of the printed test image and the lth part of the characteristic information of the corresponding frequency domain image.
[0089] Step 14.2, using the gradient descent method to update the printing parameters of the printer, and control the printer to print the print test image on the print medium using the updated printing parameters, and return to step 12, scan the print content on the print medium output by the printer, and obtain the scanned image step until the printing loss of the print test image converges, and use the printing parameters when the printing loss converges as the printing parameters after the printer is calibrated.
[0090] Among them, the convergence of printing loss means that the value of printing loss gradually decreases and tends to be stable, reaching a small level that is almost no longer changing. At this time, it also means that the printing parameters have reached the optimal parameter configuration. That is, through repeated cycles, a non-manual and automatic printing parameter calibration solution is finally realized, which can adjust the system according to the dynamic printing effects of different batches of products, and record the output configuration information in the batch equipment to achieve the purpose of optimizing the printing effect.
[0091] In summary, since the present application calibrates the printing parameters in combination with the print content output by the current printer and the original print test image, the calibration method of the present application can adjust the printing parameters of different batches of printers to different degrees, making the automatic printer calibration method of the present application highly adaptable. At the same time, since the calibration process is automatic, it can greatly reduce manpower consumption, shorten the calibration time, and achieve the effect of reducing the calibration cost.
[0092] The following is an exemplary description of the automatic printer calibration device and related equipment provided by the present application in conjunction with specific embodiments.
[0093] like Figure 2 As shown, the printer automatic calibration device 200 provided in the embodiment of the present application includes:
[0094] A first acquisition module 201 is used to acquire the inspection features of the printed test image;
[0095] The scanning module 202 is used to scan the printed content on the printing medium output by the printer to obtain a scanned image; the printed content is obtained by the printer printing a print test image on the printing medium;
[0096] The second acquisition module 203 is used to acquire the inspection features of the scanned image;
[0097] The calibration module 204 is used to automatically calibrate the printing parameters of the printer based on the inspection features of the scanned image and the inspection features of the printed test image.
[0098] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / modules are based on the same concept as the method embodiment of the present application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.
[0099] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.
[0100] like Figure 3 As shown, an embodiment of the present application provides a terminal device, such as Figure 3 As shown, the terminal device D10 of this embodiment includes: at least one processor D100 ( Figure 3 Only one processor is shown in the figure), a memory D101, and a computer program D102 stored in the memory D101 and executable on the at least one processor D100, wherein the processor D100 implements the steps of any of the above-mentioned method embodiments when executing the computer program D102.
[0101] Specifically, when the processor D100 executes the computer program D102, the print content output by the printer is scanned to obtain a scanned image, and the print parameters of the printer are automatically calibrated based on the inspection features of the scanned image and the original print test image corresponding to the scanned image. Among them, since the print parameters are calibrated in combination with the print content output by the current printer and the original print test image, the print parameters of different batches of printers can be adjusted to different degrees, making the automatic printer calibration method of the present application highly adaptable. At the same time, since the calibration process is performed automatically, it can greatly reduce manpower consumption, shorten calibration time, and achieve the effect of reducing calibration costs.
[0102] The processor D100 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.
[0103] In some embodiments, the memory D101 may be an internal storage unit of the terminal device D10, such as a hard disk or memory of the terminal device D10. In other embodiments, the memory D101 may also be an external storage device of the terminal device D10, such as a plug-in hard disk, a smart memory card (SMC, SmartMedia Card), a secure digital (SD, Secure Digital) card, a flash card (Flash Card), etc. equipped on the terminal device D10. Further, the memory D101 may also include both an internal storage unit of the terminal device D10 and an external storage device. The memory D101 is used to store an operating system, an application program, a boot loader (BootLoader), data and other programs, such as the program code of the computer program, etc. The memory D101 may also be used to temporarily store data that has been output or is to be output.
[0104] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / units are based on the same concept as the method embodiment of the present application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.
[0105] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.
[0106] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the above-mentioned method embodiments can be implemented.
[0107] An embodiment of the present application provides a computer program product. When the computer program product is run on a terminal device, the terminal device can implement the steps in the above-mentioned method embodiments when executing the computer program product.
[0108] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may at least include: any entity or device that can carry the computer program code to the image defogging device / terminal device, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, RandomAccess Memory), electric carrier signal, telecommunication signal and software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.
[0109] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.
[0110] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.
[0111] In the embodiments provided in the present application, it should be understood that the disclosed devices / network equipment and methods can be implemented in other ways. For example, the device / network equipment embodiments described above are merely schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.
[0112] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0113] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.
Claims
1. A method for automatic calibration of a printer, characterized in that: include: obtaining inspection features of a printed test image; Scanning the printed content on the print medium output by the printer to obtain a scanned image; The printed content is obtained by the printer printing a print test image on the print medium; Acquiring inspection features of the scanned image; The printing parameters of the printer are automatically calibrated based on the verification features of the scanned image and the verification features of the printed test image.
2. The printer automatic calibration method according to claim 1, characterized in that: The obtaining of the inspection feature of the scanned image comprises: Acquire a frequency domain image of the scanned image; taking at least one of the scanned image and the frequency domain image as a test object; Acquire feature information of the inspection object, and use the feature information of the inspection object as the inspection feature of the scanned image.
3. The printer automatic calibration method according to claim 2, characterized in that: The acquiring of the frequency domain image of the scanned image comprises: Perform Fourier transform on the scanned image to obtain a frequency domain image of the scanned image.
4. The printer automatic calibration method according to claim 2, characterized in that: If the inspection object is the scanned image, the acquiring of feature information of the inspection object includes: A fully convolutional neural network is used to extract features from the scanned image, and a gated recurrent unit is used to calculate the extracted features to obtain feature information of the scanned image.
5. The printer automatic calibration method according to claim 2, characterized in that: If the inspection object is the frequency domain image, the acquiring of feature information of the inspection object includes: Performing filtering processing on the frequency domain image, and dividing the filtered frequency domain image into L frequency domain images; Use the long short-term memory network to calculate each frequency domain image and obtain the hidden state vector corresponding to each frequency domain image; Perform weighted averaging on the hidden state vectors corresponding to the L frequency domain images; The result of weighted average processing is calculated using a long short-term memory network to obtain feature information of the frequency domain image.
6. The printer automatic calibration method according to claim 1, characterized in that: The automatic calibration of the printing parameters of the printer based on the inspection features of the scanned image and the inspection features of the printed test image includes: calculating a printing loss of the printed test image based on the inspection feature of the scanned image and the inspection feature of the printed test image; The printing parameters of the printer are updated using the gradient descent method, and the printer is controlled to print the printing test image on the printing medium using the updated printing parameters, and the step of returning to the step of scanning the printed content on the printing medium output by the printer to obtain the scanned image is performed until the printing loss of the printing test image converges, and the printing parameters when the printing loss converges are used as the printing parameters after the printer is calibrated.
7. The printer automatic calibration method according to claim 6, characterized in that: The calculating the printing loss of the printed test image based on the inspection feature of the scanned image and the inspection feature of the printed test image comprises: The inspection features of the scanned image and the inspection features of the printed test image are calculated by a cross entropy loss function to obtain a printing loss of the printed test image.
8. A printer automatic calibration device, characterized in that: include: A first acquisition module, used for acquiring inspection features of a printed test image; A scanning module, used for scanning the printed content on the printing medium output by the printer to obtain a scanned image; The printed content is obtained by the printer printing a print test image on the print medium; A second acquisition module, used to acquire the inspection features of the scanned image; A calibration module is used to automatically calibrate the printing parameters of the printer based on the inspection features of the scanned image and the inspection features of the printed test image.
9. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the printer automatic calibration method according to any one of claims 1 to 7 is implemented.
10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method for automatic calibration of a printer as claimed in any one of claims 1 to 7 is implemented.